Plugins

Un plugin de poste de travail scientifique reproductible pour DeepSeek Harness : cellules pilotées par l'agent, figures en ligne avec retour/réexécution, provenance par manifeste et instantanés d'environnement.

Observabilité Langfuse pour DeepSeek Harness : exporte les journaux de session en traces OpenTelemetry (conventions sémantiques GenAI) vers l'endpoint OTLP de Langfuse.

Génération de PPTX stable et modifiable pour agents IA — IR sémantique en entrée, DrawingML natif en sortie.

Ajoute des outils Git (status, diff, log, commit, branch, et checkpoint optionnel) protégés par approbation.

Sonneries de fin de tâche par espace de travail, plus des sons d'alerte pour l'approbation, les questions, la revue de plan, le blocage d'objectif et l'échec de tâche, avec synthèse intégrée, voix (TTS) et audio personnalisé.

Analyse les skills et les configurations MCP à la recherche d'injections de prompt, d'homoglyphes, d'Unicode caché, de commandes shell dangereuses et de fuites d'identifiants.

Opérations ADB d'appareils et de banc de test pour DSH : découverte d'appareils, logcat structuré (streaming en arrière-plan), installation d'apk, pull/push de fichiers, et instantanés de performance dumpsys.

DeepSeek Harness plugin: panel hotkeys for every interaction panel — Enter presses the confirm (primary) button, Esc presses the cancel button (approval, question/choice, plan review; Claude Code habits).

Voice input (Web Speech API) and read-aloud (speechSynthesis) for the DeepSeek Harness web GUI — DSH 语音输入 + 回复朗读套件

DSH plugin: password gate for remote (non-loopback) /api access (passwordless by default), unblock the loopback-pinned privileged endpoints, restore everything on uninstall, and give the local 127.0.0.1 user the native OS folder picker for workspace selec

Multimodal plugin for DeepSeek Harness: understand images and generate images through configurable OpenAI-compatible or DashScope endpoints.

生物信息学「许愿式分析」插件：BioPython 全功能覆盖（任意代码执行器 bio_python + 14 个领域 skill）+ 高频语义化工具 + 零依赖自举 Python 环境（uv + venv + biopython 自动下载到插件私有目录）。用户下载安装即可许愿式分析。

Adds the DeepSeek Harness homepage background to dsh web: WebGL fluid light, dot-line grid and a digital point-cloud whale, with dark and light palettes.

Turns a stated need into a plugin choice: an agent skill that queries a catalog of the whole `dsh-plugin` topic (2600+ repos, recrawled every 6 hours, Chinese descriptions from Workers AI) through a ranked search API, then hands back the matching `dsh plugin add` command.

Pre-install supply-chain poison scanner for DSH plugins: AST (JS-X-Ray) + deobfuscation + regex heuristics, exits non-zero on findings for CI gating.

Exposes bounded Prometheus metrics for DSH sessions, agents, LLM calls, tools, approvals, subagents, and jobs, with a Grafana dashboard and a loopback-only endpoint by default.

Agent-initiated voice calls: `offer_call` rings the human (接听/拒接/稍后再说); accepted calls synthesize and play locally via CrispASR + Qwen3-TTS (9 speakers, 2 Chinese dialects), rejected calls return the decision to the agent.

Free voice closed loop for the Web UI: browser SpeechRecognition mic input with live interim results plus read-aloud speaker buttons and auto-read for assistant replies, zero configuration and no API key.

Voice AI girlfriend for the Web UI: FunASR mic input, Qwen3-TTS spoken replies, companion animation window, and two-way QQ chat (text/voice/image push) via NapCat.

Speech-to-text voice input for the web UI: a mic button in the composer transcribes speech into the draft via the browser Web Speech API (zero-config) or an OpenAI-compatible Whisper API (OpenAI / Groq), with a selectable model and language in Settings.

Model-facing image_describe (识图) tool over the DashScope OpenAI-compatible API (qwen3.7-flash), plus a paste bridge: on text-only sessions, pasted images auto-convert to file paths at send time and render back in the transcript, so they never trip image admission. Bring your own DASHSCOPE_API_KEY; endpoint/model/budgets configurable, redirect-proof HTTP client, works in every agent preset.

Agent-callable vision tool that describes local images via any OpenAI-compatible vision endpoint you configure, with an optional multi-model cross-check and no built-in keys.

On-demand vision for text-only DeepSeek models: upload images, and the model calls a view_image tool backed by any OpenAI-compatible vision endpoint (Qwen/DashScope by default).